wiki_8000er_deaths <- "List of deaths on eight-thousanders"
wiki_800er <- "Eight-thousander"
wiki_everest <- "List of people who died climbing Mount Everest"

# eightthousander_names <- c("Everest", "K2", "Kangchenjunga", "Lhotse",
#                      "Makalu", "Cho Oyu", "Dhaulagiri I", "Manaslu",
#                      "Nanga Parbat", "Annapurna I", "Gasherbrum I",
#                      "Broad Peak", "Gasherbrum II", "Shishapangma")
# 

get_wiki_tables <- function(title){
    wiki_api <- "https://en.wikipedia.org/w/api.php"

    params <- list(action = "parse", 
                   page = title, 
                   format = "xml")
  
    webdata <- GET(url = wiki_api, query = params)
    webdata_xml <- content(webdata)
  
    page_html <- read_html(xml_text(webdata_xml))
    table_elements <- html_nodes(x = page_html, css =".wikitable")

    table_elements
}

convert_table <- function(wikitable){
  html_table(wikitable) %>% 
    clean_names()
}

# get mountain names from Wikipedia page on 8000ers
eightthousanders <- get_wiki_tables(wiki_800er)

eightthou_summary <- html_table(eightthousanders[1])[[1]] %>% 
  clean_names()

colnames(eightthou_summary) <- eightthou_summary %>% 
    slice(1) %>% 
    unlist(use.names = FALSE)

eightthou_summary_cleaned <-  eightthou_summary %>% 
  janitor::clean_names() %>% 
  slice(-1) %>% 
  # add info re mountain range
  mutate(range = case_when(str_detect(country,"Pakistan") ~ "Karakoram",
                           TRUE ~ "Himalayas")) %>% 
  # fix height info
  mutate(height = as.integer(
    str_remove(
      str_extract(height_24,"8,[:digit:]{3}"),
      ",")))

eightthou_names <- eightthou_summary_cleaned %>% 
  select(name) %>% 
  pull()

# get all tables from deaths on 8000ers Wikipedia page
mountains2_14 <- get_wiki_tables(wiki_8000er_deaths)

# convert html to df; creates a list of dfs
mountains2_14_dfs <- mountains2_14 %>% 
  map(convert_table)

# specify names using the list of mountains from other Wikipedia page
names(mountains2_14_dfs) <- eightthou_names[2:14]

# add mountain names prior to joining dfs
# not elegant but can't figure out how else to do this at the moment
for (i in seq(1,length(mountains2_14_dfs))){
  mountains2_14_dfs[i][[1]] <- mutate(mountains2_14_dfs[i][[1]], 
         mountain = names(mountains2_14_dfs[i]))
}

# reduce list to a single df
deaths_no_everest <- mountains2_14_dfs %>% 
  reduce(bind_rows) %>% 
  select(-x,-references)

everest_deaths <- get_wiki_tables(wiki_everest)[1][[1]] %>% 
  convert_table() %>% 
  mutate(mountain = "Everest") %>% 
  select(date, name, nationality, cause_of_death, mountain)

all_8000er_deaths <- bind_rows(everest_deaths,
                               deaths_no_everest)

# save to disk just in case
# saveRDS(all_8000er_deaths, file = "all_8000er_deaths.rds")

all_8000er_deaths %>% 
  count(mountain) %>% 
  mutate(mountain = fct_reorder(mountain,n)) %>% 
  ggplot(aes(x = n, y = mountain)) +
  geom_col(fill = "lightseagreen") +
  labs(
    x = "Number of deaths",
    y = "",
    title = "Deaths on 8000ers"
  ) +
  theme_light()

eightthou_ascents <- eightthou_summary_cleaned %>% 
  select(name, height, total_ascents_c, range) %>% 
  mutate(total_ascents_c = as.integer(total_ascents_c),
    prop_ascents = total_ascents_c / sum(total_ascents_c))

eightthou_ascents %>% 
  mutate(name = fct_reorder(name,prop_ascents)) %>% 
  ggplot(aes(x = prop_ascents, y = name, fill = range)) +
  geom_col() +
  scale_fill_brewer(palette = "Dark2") +
  labs(
    x = "Proportion of ascents (1950-2012)",
    y = "",
    title = "Which 8000ers are climbed the most?",
    fill = "Range"
  ) +
  theme_light()

eightthou_ascents %>% 
  mutate(name = fct_reorder(name,height)) %>% 
  ggplot(aes(x = height, y = name, colour = range, size = prop_ascents)) +
  geom_point() +
  scale_colour_brewer(palette = "Dark2") +
    labs(
    x = "Height (m)",
    y = "",
    title = "Higher ≠ more ascents",
    subtitle = "(except for Everest)",
    colour = "Range"
  ) +
  guides(size = "none") +
  theme_light()

all_8000er_deaths %>% 
  count(mountain) %>% 
  mutate(prop_deaths = n / sum(n)) %>% 
  inner_join(eightthou_ascents, by = c("mountain" = "name")) %>% 
  mutate(deaths_weighted = prop_deaths / prop_ascents,
         mountain = fct_reorder(mountain,deaths_weighted)) %>% 
  ggplot(aes(x = deaths_weighted, y = mountain, colour = range)) +
  geom_point(size = 2) +
  geom_segment(aes(xend = 1, yend = mountain)) +
  geom_vline(xintercept = 1, linetype = 2) +
  scale_colour_brewer(palette = "Dark2") +
   labs(
    x = "Ratio of deaths to ascents",
    y = "",
    title = "Which 8000ers are deadliest?",
    colour = "Range"
  ) +
  theme_light()

unigrams <- all_8000er_deaths %>% 
  mutate(index = row_number()) %>% 
  unnest_tokens(output = cause_unigrams, input = cause_of_death) %>% 
  anti_join(stop_words, by = c("cause_unigrams"="word"))

causes <- unigrams %>% 
  count(cause_unigrams, sort = TRUE) 


causes %>% 
  datatable(caption = "Cause of death (unigrams)",
            colnames = c("Unigram","Count"))

wordcloud(words = causes$cause_unigrams, freq = causes$n,
          colors = brewer.pal(8,"Dark2"))

cause_per_mountain <- unigrams %>% 
  count(cause_unigrams, mountain) %>% 
  group_by(mountain) %>% 
  ungroup()

# function to create a wordcloud for individual mountains
mountain_cloud <- function(mname){
  m <- cause_per_mountain %>% 
    filter(mountain == mname)
  
  wordcloud(words = m$cause_unigrams, freq = m$n,
          colors = brewer.pal(8,"Dark2"))
}

deaths_per_year <- all_8000er_deaths %>% 
  mutate(year = as.integer(str_extract(date,"[:digit:]{4}"))) %>% 
  count(mountain, year, sort = TRUE)


p <- deaths_per_year %>% 
  filter(year >= 2000) %>% 
  ggplot(aes(x = year, y = n, colour = mountain)) +
  geom_point() +
  geom_line() +
  gghighlight(mountain %in% c("Everest","K2", "Manaslu", "Nanga Parbat")) +
  scale_colour_brewer(palette = "Dark2") +
  theme_light() +
  labs(
    title = "Deadliest years since 2000",
    x = "Year",
    y = "Number of deaths"
  )

ggplotly(p)